path: root/block/bfq-iosched.h

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * Header file for the BFQ I/O scheduler: data structures and
 * prototypes of interface functions among BFQ components.
 */
#ifndef _BFQ_H
#define _BFQ_H

#include <linux/blktrace_api.h>
#include <linux/hrtimer.h>
#include <linux/blk-cgroup.h>

#include "blk-cgroup-rwstat.h"

#define BFQ_IOPRIO_CLASSES	3
#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)

#define BFQ_MIN_WEIGHT			1
#define BFQ_MAX_WEIGHT			1000
#define BFQ_WEIGHT_CONVERSION_COEFF	10

#define BFQ_DEFAULT_QUEUE_IOPRIO	4

#define BFQ_WEIGHT_LEGACY_DFL	100
#define BFQ_DEFAULT_GRP_IOPRIO	0
#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE

#define MAX_PID_STR_LENGTH 12

/*
 * Soft real-time applications are extremely more latency sensitive
 * than interactive ones. Over-raise the weight of the former to
 * privilege them against the latter.
 */
#define BFQ_SOFTRT_WEIGHT_FACTOR	100

struct bfq_entity;

/**
 * struct bfq_service_tree - per ioprio_class service tree.
 *
 * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
 * ioprio_class has its own independent scheduler, and so its own
 * bfq_service_tree.  All the fields are protected by the queue lock
 * of the containing bfqd.
 */
struct bfq_service_tree {
	/* tree for active entities (i.e., those backlogged) */
	struct rb_root active;
	/* tree for idle entities (i.e., not backlogged, with V < F_i)*/
	struct rb_root idle;

	/* idle entity with minimum F_i */
	struct bfq_entity *first_idle;
	/* idle entity with maximum F_i */
	struct bfq_entity *last_idle;

	/* scheduler virtual time */
	u64 vtime;
	/* scheduler weight sum; active and idle entities contribute to it */
	unsigned long wsum;
};

/**
 * struct bfq_sched_data - multi-class scheduler.
 *
 * bfq_sched_data is the basic scheduler queue.  It supports three
 * ioprio_classes, and can be used either as a toplevel queue or as an
 * intermediate queue in a hierarchical setup.
 *
 * The supported ioprio_classes are the same as in CFQ, in descending
 * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
 * Requests from higher priority queues are served before all the
 * requests from lower priority queues; among requests of the same
 * queue requests are served according to B-WF2Q+.
 *
 * The schedule is implemented by the service trees, plus the field
 * @next_in_service, which points to the entity on the active trees
 * that will be served next, if 1) no changes in the schedule occurs
 * before the current in-service entity is expired, 2) the in-service
 * queue becomes idle when it expires, and 3) if the entity pointed by
 * in_service_entity is not a queue, then the in-service child entity
 * of the entity pointed by in_service_entity becomes idle on
 * expiration. This peculiar definition allows for the following
 * optimization, not yet exploited: while a given entity is still in
 * service, we already know which is the best candidate for next
 * service among the other active entities in the same parent
 * entity. We can then quickly compare the timestamps of the
 * in-service entity with those of such best candidate.
 *
 * All fields are protected by the lock of the containing bfqd.
 */
struct bfq_sched_data {
	/* entity in service */
	struct bfq_entity *in_service_entity;
	/* head-of-line entity (see comments above) */
	struct bfq_entity *next_in_service;
	/* array of service trees, one per ioprio_class */
	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
	/* last time CLASS_IDLE was served */
	unsigned long bfq_class_idle_last_service;

};

/**
 * struct bfq_weight_counter - counter of the number of all active queues
 *                             with a given weight.
 */
struct bfq_weight_counter {
	unsigned int weight; /* weight of the queues this counter refers to */
	unsigned int num_active; /* nr of active queues with this weight */
	/*
	 * Weights tree member (see bfq_data's @queue_weights_tree)
	 */
	struct rb_node weights_node;
};

/**
 * struct bfq_entity - schedulable entity.
 *
 * A bfq_entity is used to represent either a bfq_queue (leaf node in the
 * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
 * entity belongs to the sched_data of the parent group in the cgroup
 * hierarchy.  Non-leaf entities have also their own sched_data, stored
 * in @my_sched_data.
 *
 * Each entity stores independently its priority values; this would
 * allow different weights on different devices, but this
 * functionality is not exported to userspace by now.  Priorities and
 * weights are updated lazily, first storing the new values into the
 * new_* fields, then setting the @prio_changed flag.  As soon as
 * there is a transition in the entity state that allows the priority
 * update to take place the effective and the requested priority
 * values are synchronized.
 *
 * Unless cgroups are used, the weight value is calculated from the
 * ioprio to export the same interface as CFQ.  When dealing with
 * "well-behaved" queues (i.e., queues that do not spend too much
 * time to consume their budget and have true sequential behavior, and
 * when there are no external factors breaking anticipation) the
 * relative weights at each level of the cgroups hierarchy should be
 * guaranteed.  All the fields are protected by the queue lock of the
 * containing bfqd.
 */
struct bfq_entity {
	/* service_tree member */
	struct rb_node rb_node;

	/*
	 * Flag, true if the entity is on a tree (either the active or
	 * the idle one of its service_tree) or is in service.
	 */
	bool on_st_or_in_serv;

	/* B-WF2Q+ start and finish timestamps [sectors/weight] */
	u64 start, finish;

	/* tree the entity is enqueued into; %NULL if not on a tree */
	struct rb_root *tree;

	/*
	 * minimum start time of the (active) subtree rooted at this
	 * entity; used for O(log N) lookups into active trees
	 */
	u64 min_start;

	/* amount of service received during the last service slot */
	int service;

	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
	int budget;

	/* device weight, if non-zero, it overrides the default weight of
	 * bfq_group_data */
	int dev_weight;
	/* weight of the queue */
	int weight;
	/* next weight if a change is in progress */
	int new_weight;

	/* original weight, used to implement weight boosting */
	int orig_weight;

	/* parent entity, for hierarchical scheduling */
	struct bfq_entity *parent;

	/*
	 * For non-leaf nodes in the hierarchy, the associated
	 * scheduler queue, %NULL on leaf nodes.
	 */
	struct bfq_sched_data *my_sched_data;
	/* the scheduler queue this entity belongs to */
	struct bfq_sched_data *sched_data;

	/* flag, set to request a weight, ioprio or ioprio_class change  */
	int prio_changed;

	/* flag, set if the entity is counted in groups_with_pending_reqs */
	bool in_groups_with_pending_reqs;
};

struct bfq_group;

/**
 * struct bfq_ttime - per process thinktime stats.
 */
struct bfq_ttime {
	/* completion time of the last request */
	u64 last_end_request;

	/* total process thinktime */
	u64 ttime_total;
	/* number of thinktime samples */
	unsigned long ttime_samples;
	/* average process thinktime */
	u64 ttime_mean;
};

/**
 * struct bfq_queue - leaf schedulable entity.
 *
 * A bfq_queue is a leaf request queue; it can be associated with an
 * io_context or more, if it  is  async or shared  between  cooperating
 * processes. @cgroup holds a reference to the cgroup, to be sure that it
 * does not disappear while a bfqq still references it (mostly to avoid
 * races between request issuing and task migration followed by cgroup
 * destruction).
 * All the fields are protected by the queue lock of the containing bfqd.
 */
struct bfq_queue {
	/* reference counter */
	int ref;
	/* parent bfq_data */
	struct bfq_data *bfqd;

	/* current ioprio and ioprio class */
	unsigned short ioprio, ioprio_class;
	/* next ioprio and ioprio class if a change is in progress */
	unsigned short new_ioprio, new_ioprio_class;

	/* last total-service-time sample, see bfq_update_inject_limit() */
	u64 last_serv_time_ns;
	/* limit for request injection */<